Scene Flow Estimation Based on Adaptive Anisotropic Total Variation Flow-Driven Method

Figure 4

Cones of Middlebury stereo datasets. (a) and (b) are left and right image in time . (c) and (d) are ground truth disparity maps. (e) and (f) are left and right image in time . (g) is ground truth of optical flow in horizontal direction. (h) is ground truth of optical flow in vertical direction.

(a)

(b)

(c)

(d)

(e)

(f)

(g)

(h)